Image-Text-to-Text
MLX
Safetensors
gemma4
rotorquant
kv-cache-quantization
gemma
multimodal
quantized
2bit
2-bit
Instructions to use majentik/gemma-4-E4B-RotorQuant-MLX-2bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use majentik/gemma-4-E4B-RotorQuant-MLX-2bit with MLX:
# Make sure mlx-vlm is installed # pip install --upgrade mlx-vlm from mlx_vlm import load, generate from mlx_vlm.prompt_utils import apply_chat_template from mlx_vlm.utils import load_config # Load the model model, processor = load("majentik/gemma-4-E4B-RotorQuant-MLX-2bit") config = load_config("majentik/gemma-4-E4B-RotorQuant-MLX-2bit") # Prepare input image = ["http://images.cocodataset.org/val2017/000000039769.jpg"] prompt = "Describe this image." # Apply chat template formatted_prompt = apply_chat_template( processor, config, prompt, num_images=1 ) # Generate output output = generate(model, processor, formatted_prompt, image) print(output) - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
- Atomic Chat
Fix quantization metadata: top-level bits 2 (matches tensor data)
Browse files- config.json +2 -2
config.json
CHANGED
|
@@ -55,7 +55,7 @@
|
|
| 55 |
"model_type": "gemma4",
|
| 56 |
"quantization": {
|
| 57 |
"group_size": 64,
|
| 58 |
-
"bits":
|
| 59 |
"mode": "affine"
|
| 60 |
},
|
| 61 |
"quantization_config": {
|
|
@@ -201,4 +201,4 @@
|
|
| 201 |
"use_clipped_linears": true
|
| 202 |
},
|
| 203 |
"vision_soft_tokens_per_image": 280
|
| 204 |
-
}
|
|
|
|
| 55 |
"model_type": "gemma4",
|
| 56 |
"quantization": {
|
| 57 |
"group_size": 64,
|
| 58 |
+
"bits": 2,
|
| 59 |
"mode": "affine"
|
| 60 |
},
|
| 61 |
"quantization_config": {
|
|
|
|
| 201 |
"use_clipped_linears": true
|
| 202 |
},
|
| 203 |
"vision_soft_tokens_per_image": 280
|
| 204 |
+
}
|